---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
tags:
- lora
- llama2
- mmlu
- data-selection
---

# offline-embedding

Offline training with **embedding**-based retrieved data (2.5% of full dataset).

> **Note**: This checkpoint is from a **single random seed** (seed=3) and a specific training step (step 1040). Results may vary across seeds.

## Details

| Key | Value |
|-----|-------|
| Base model | `meta-llama/Llama-2-7b-hf` |
| Task | MMLU |
| Data selection | Embedding Retrieval |
| Data ratio | 2.5% |
| Online | False |
| LoRA rank | 128 |
| LoRA alpha | 512 |
| Target modules | q_proj, k_proj, v_proj, o_proj |
| Seed | 3 |
| Checkpoint step | 1040 |

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
model = PeftModel.from_pretrained(base_model, "DATA-ADAPT/offline-embedding")
tokenizer = AutoTokenizer.from_pretrained("DATA-ADAPT/offline-embedding")
```